CN107665354A - Identify the method and device of identity card - Google Patents
Identify the method and device of identity card Download PDFInfo
- Publication number
- CN107665354A CN107665354A CN201710852421.0A CN201710852421A CN107665354A CN 107665354 A CN107665354 A CN 107665354A CN 201710852421 A CN201710852421 A CN 201710852421A CN 107665354 A CN107665354 A CN 107665354A
- Authority
- CN
- China
- Prior art keywords
- target image
- character
- identity card
- neural networks
- card
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Character Discrimination (AREA)
Abstract
The disclosure is directed to a kind of method and device for identifying identity card.This method includes：In the case where determining that target image includes identity card by the first full convolutional network, the character region in the target image is determined by the second full convolutional network；The character of the character region in the target image is identified by the 3rd convolutional neural networks；Character in the target image determines the ID card information in the target image.The disclosure can quickly and accurately identify the ID card information in image.
Description
Technical field
This disclosure relates to technical field of computer vision, more particularly to the method and device of identification identity card.
Background technology
Identity card, also known as resident identification card, it is a kind of legal certificate for proving holder's identity, more by various countries or ground
Citizen is given in district government's distribution.Identity card can be as the proof instrument of everyone unique citizenship.How it is quick and
Identity card is identified exactly, the problem of being urgent need to resolve.
The content of the invention
To overcome problem present in correlation technique, the disclosure provides a kind of method and device for identifying identity card.
According to the first aspect of the embodiment of the present disclosure, there is provided a kind of method for identifying identity card, including：
In the case where determining that target image includes identity card by the first full convolutional network, pass through the second full convolution net
Network determines the character region in the target image；
The character of the character region in the target image is identified by the 3rd convolutional neural networks；
Character in the target image determines the ID card information in the target image.
In a kind of possible implementation, methods described also includes：
The probability for being categorized as identity card belonging to the target image is determined by the described first full convolutional network；
In the case where the probability for being categorized as identity card belonging to the target image meets condition, the target figure is determined
As including identity card.
In a kind of possible implementation, the character place in the target image is determined by the second full convolutional network
Region, including：
Identity card region is intercepted from the target image, obtains ID Card Image；
The ID Card Image is inputted in the second full convolutional network；
The character region in the ID Card Image is determined by the described second full convolutional network.
In a kind of possible implementation, the character institute in the target image is identified by the 3rd convolutional neural networks
Character in region, including：
Character region is intercepted from the ID Card Image, obtains character picture；
The character picture is inputted in the 3rd convolutional neural networks；
The character in the character picture is identified by the 3rd convolutional neural networks.
In a kind of possible implementation, methods described also includes：
Determined by the described first full convolutional network belonging to the target image be categorized as the probability of identity card before,
Train the first convolutional neural networks for identifying the positive and negative of identity card and the bounding box of identity card；
First convolutional neural networks are converted into the described first full convolutional network.
In a kind of possible implementation, methods described also includes：
Before the character region during the target image is determined by the second full convolutional network, train for identifying
Second convolutional neural networks of character region；
Second convolutional neural networks are converted into the described second full convolutional network.
According to the second aspect of the embodiment of the present disclosure, there is provided a kind of device for identifying identity card, including：
First determining module, for determining that target image includes the situation of identity card by the first full convolutional network
Under, the character region in the target image is determined by the second full convolutional network；
Identification module, for identifying the word of the character region in the target image by the 3rd convolutional neural networks
Symbol；
3rd determining module, the identity card letter in the target image is determined for the character in the target image
Breath.
In a kind of possible implementation, described device also includes：
3rd determining module, for determining to be categorized as body belonging to the target image by the described first full convolutional network
The probability of part card；
4th determining module, for meeting the situation of condition in the probability for being categorized as identity card belonging to the target image
Under, determine that the target image includes identity card.
In a kind of possible implementation, first determining module includes：
First interception submodule, for intercepting identity card region from the target image, obtains ID Card Image；
First input submodule, for the ID Card Image to be inputted in the second full convolutional network；
Determination sub-module, for determining the character location in the ID Card Image by the described second full convolutional network
Domain.
In a kind of possible implementation, the identification module includes：
Second interception submodule, for intercepting character region from the ID Card Image, obtains character picture；
Second input submodule, for the character picture to be inputted in the 3rd convolutional neural networks；
Submodule is identified, for identifying the character in the character picture by the 3rd convolutional neural networks.
In a kind of possible implementation, described device also includes：
First training module, for determining to be categorized as belonging to the target image by the described first full convolutional network
Before the probability of identity card, the first convolution nerve net for identifying the positive and negative of identity card and the bounding box of identity card is trained
Network；
First modular converter, for first convolutional neural networks to be converted into the described first full convolutional network.
In a kind of possible implementation, described device also includes：
Second training module, for the character region in the target image is determined by the second full convolutional network
Before, the second convolutional neural networks for identifying character region are trained；
Second modular converter, for second convolutional neural networks to be converted into the described second full convolutional network.
According to the third aspect of the embodiment of the present disclosure, there is provided a kind of device for identifying identity card, including：Processor；For
Store the memory of processor-executable instruction；Wherein, the processor is configured as the method for performing above-mentioned identification identity card.
According to the fourth aspect of the embodiment of the present disclosure, there is provided a kind of non-transitorycomputer readable storage medium, when described
When instruction in storage medium is by computing device so that the method that processor is able to carry out above-mentioned identification identity card.
The technical scheme provided by this disclosed embodiment can include the following benefits：Passing through the first full convolutional network
In the case of determining target image and including identity card, the character location in target image is determined by the second full convolutional network
Domain, by the character of the character region in the 3rd convolutional neural networks recognition target image, and according in target image
Character determines the ID card information in target image, thus, it is possible to quickly and accurately identify the ID card information in image.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
Accompanying drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the disclosure
Example, and be used to together with specification to explain the principle of the disclosure.
Fig. 1 is a kind of flow chart of the method for identification identity card according to an exemplary embodiment.
Fig. 2 be a kind of identification identity card according to an exemplary embodiment method and step S11 in it is complete by second
Convolutional network determines an exemplary flow chart of the character region in target image.
Fig. 3 is the bounding box of the identity card in a kind of method of identification identity card according to an exemplary embodiment
Schematic diagram.
Fig. 4 is a kind of the one exemplary of the method and step S12 of identification identity card according to an exemplary embodiment
Flow chart.
Fig. 5 is showing for the bounding box of the character in a kind of method of identification identity card according to an exemplary embodiment
It is intended to.
Fig. 6 is a kind of device block diagram of identification identity card according to an exemplary embodiment.
Fig. 7 is an a kind of exemplary block diagram of the device of identification identity card according to an exemplary embodiment.
Fig. 8 is a kind of block diagram for being used to identify the device 800 of identity card according to an exemplary embodiment.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the disclosure.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects be described in detail in claims, the disclosure.
Fig. 1 is a kind of flow chart of the method for identification identity card according to an exemplary embodiment.This method can be with
Applied in terminal device.As shown in figure 1, the method comprising the steps of S11 to step S13.
In step s 11, in the case where determining that target image includes identity card by the first full convolutional network, pass through
Second full convolutional network determines the character region in target image.
In the present embodiment, the first full convolutional network (Fully Convolutional Network, FCN) can be passed through
Determine whether include identity card in target image, identity card in target image can also be determined by the first full convolutional network
Position.For example, the bounding box of the identity card in target image can be determined by the first full convolutional network.
In the present embodiment, character can include Chinese character and numeral etc., be not limited thereto.Second full convolutional network can be with
The side of character is determined for determining to whether there is character in target image, and in the case of there can be character in the target image
Boundary's frame.
In step s 12, the character of the character region in the 3rd convolutional neural networks recognition target image is passed through.
In the present embodiment, the 3rd convolutional neural networks (Convolutional Neural Network, CNN) are based on step
Character region in the target image that rapid S11 is determined, identifies character.
In step s 13, the character in target image determines the ID card information in target image.
In a kind of possible implementation, the character and character region in target image are in target image
In position, it may be determined that the ID card information in target image.Wherein, ID card information can include name, sex, the people
At least one of in race, date of birth, address, citizen ID certificate number, issuing authority and period of validity.For example, according to target
The position of numeral and numeral in the target image in image, it may be determined that digital order, may thereby determine that citizenship
Demonstrate,prove number.
The present embodiment passes through second in the case where determining that target image includes identity card by the first full convolutional network
Full convolutional network determines the character region in target image, passes through the word in the 3rd convolutional neural networks recognition target image
The character of region is accorded with, and the character in target image determines the ID card information in target image, thus, it is possible to fast
ID card information in speed and exactly identification image.
In a kind of possible implementation, this method also includes：Target image institute is determined by the first full convolutional network
The probability for being categorized as identity card of category；In the case where the probability for being categorized as identity card belonging to target image meets condition, really
The image that sets the goal includes identity card.
In the present embodiment, the first full convolutional network can classify to target image, determine belonging to target image
It is categorized as the probability of identity card.
In a kind of possible implementation, it can determine to be categorized as belonging to target image by the first full convolutional network
The positive probability of identity card, and can determine to be categorized as identity card reverse side belonging to target image by the first full convolutional network
Probability.
In a kind of possible implementation, first can be more than in the probability for being categorized as identity card belonging to target image
In the case of threshold value, determine that the probability for being categorized as identity card belonging to target image meets condition, so that it is determined that in target image
Including identity card.
In alternatively possible implementation, it may be determined that target image belongs to the probability of each classification, and can be
In the case that the probability for being categorized as identity card belonging to target image is more than the probability of every other classification, target image institute is determined
The probability for being categorized as identity card of category meets condition, so that it is determined that target image includes identity card.
Fig. 2 be a kind of identification identity card according to an exemplary embodiment method and step S11 in it is complete by second
Convolutional network determines an exemplary flow chart of the character region in target image.As shown in Fig. 2 step S11 can be with
Including step S111 to step S113.
In step S111, identity card region is intercepted from target image, obtains ID Card Image.
, can be according to the identity card in the target image that the first full convolutional network identifies in a kind of possible implementation
Bounding box, identity card region is intercepted from target image, obtains ID Card Image.Wherein, ID Card Image can be
Identity card direct picture or identity card verso images.
Fig. 3 is the bounding box of the identity card in a kind of method of identification identity card according to an exemplary embodiment
Schematic diagram.
In step S112, ID Card Image is inputted in the second full convolutional network.
In step S113, the character region in ID Card Image is determined by the second full convolutional network.
In this example, the second full convolutional network is determined for whether there is character in ID Card Image, and can be with
The bounding box of character is determined in the case of character in ID Card Image being present.
In this example, by being inputted by ID Card Image the second full convolutional network of input, rather than by whole target image
Second full convolutional network, it is possible to increase the speed of the second full convolutional network identification character zone.
Fig. 4 is a kind of the one exemplary of the method and step S12 of identification identity card according to an exemplary embodiment
Flow chart.As shown in figure 4, step S12 can include step S121 to step S123.
In step S121, character region is intercepted from ID Card Image, obtains character picture.
, can be according to the character in the ID Card Image that the second full convolutional network identifies in a kind of possible implementation
Bounding box, character region is intercepted from ID Card Image, obtains character picture.
Fig. 5 is showing for the bounding box of the character in a kind of method of identification identity card according to an exemplary embodiment
It is intended to.
In step S122, character picture is inputted in the 3rd convolutional neural networks.
In a kind of possible implementation, character picture is inputted in the 3rd convolutional neural networks, can be included：By word
Symbol Image Adjusting is the picture size that the 3rd convolutional neural networks are specified, and the character picture after adjustment is inputted into the 3rd convolution god
Through in network.
In step S123, the character in character picture is identified by the 3rd convolutional neural networks.
In this example, by the way that character picture is inputted in the 3rd convolutional neural networks, rather than by target image or body
Part card image is inputted in the 3rd convolutional neural networks, it is possible to increase the 3rd convolutional neural networks identify the speed of character.
In a kind of possible implementation, this method also includes：Target image is being determined by the first full convolutional network
Affiliated is categorized as before the probability of identity card, train for identify the positive and negative of identity card and the bounding box of identity card
One convolutional neural networks；First convolutional neural networks are converted into the first full convolutional network.In the implementation, it can pass through
Full articulamentum in first convolutional neural networks is converted into convolutional layer, the first convolutional neural networks are converted into the first full volume
Product network.
In alternatively possible implementation, positive and negative and identity card for identifying identity card can be directly trained
Bounding box the first full convolutional network.
In a kind of possible implementation, this method also includes：Target image is being determined by the second full convolutional network
In character region before, train the second convolutional neural networks for identifying character region；By the second convolution god
The second full convolutional network is converted to through network., can be by the way that complete in the second convolutional neural networks being connected in the implementation
Connect layer and be converted to convolutional layer, the second convolutional neural networks are converted into the second full convolutional network.
In alternatively possible implementation, the second full convolution for identifying character region can be directly trained
Network.
In the present embodiment, the first convolutional neural networks are used for positive and negative and the border of identity card for identifying identity card
Frame, the first convolutional neural networks can include multiple convolutional layers and at least one full articulamentum；Second convolutional neural networks are used for
The second convolutional neural networks of character region are identified, the second convolutional neural networks can include multiple convolutional layers and at least one
Individual full articulamentum；The character for the character region that 3rd convolutional neural networks are used in recognition target image, the 3rd convolution god
It can include multiple convolutional layers and at least one full articulamentum through network；First full convolutional neural networks can be by the first convolution god
It is converted to through network, the first full convolutional network can include multiple convolutional layers；Second full convolutional neural networks can be by second
Convolutional neural networks are converted to, and the second full convolutional network can include multiple convolutional layers.Wherein, the first convolutional neural networks,
Second convolutional neural networks and the 3rd convolutional neural networks are respectively trained.First convolutional neural networks, the second convolutional neural networks
Number with convolutional layer in the 3rd convolutional neural networks, full articulamentum can be with identical, can also be different, and the present embodiment is not made to this
Limit.For example, the first convolutional neural networks, the second convolutional neural networks and the 3rd convolutional neural networks include 5 convolution respectively
Layer and 3 full articulamentums, the first full convolutional network and the second full convolutional network include 8 convolutional layers respectively.
Fig. 6 is a kind of device block diagram of identification identity card according to an exemplary embodiment.Reference picture 6, the device
Including the first determining module 61, the determining module 63 of identification module 62 and second.
First determining module 61 is configured as determining that target image includes identity card by the first full convolutional network
In the case of, the character region in target image is determined by the second full convolutional network.
The identification module 62 is configured as by the character region in the 3rd convolutional neural networks recognition target image
Character.
The character that second determining module 63 is configured as in target image determines the identity card letter in target image
Breath.
Fig. 7 is an a kind of exemplary block diagram of the device of identification identity card according to an exemplary embodiment.Such as
Shown in Fig. 7：
In a kind of possible implementation, the device also includes the 3rd determining module 64 and the 4th determining module 65.
3rd determining module 64 is configured as determining to be categorized as body belonging to target image by the first full convolutional network
The probability of part card.
4th determining module 65 is configured as meeting condition in the probability for being categorized as identity card belonging to target image
In the case of, determine that target image includes identity card.
In a kind of possible implementation, the first determining module 61 includes the first interception input of submodule 611, first
Module 612 and determination sub-module 613.
The first interception submodule 611 is configured as intercepting identity card region from target image, obtains identity card
Image.
First input submodule 612 is configured as inputting ID Card Image in the second full convolutional network.
The determination sub-module 613 is configured as determining the character location in ID Card Image by the second full convolutional network
Domain.
In a kind of possible implementation, identification module 62 includes the second interception submodule 621, the second input submodule
622 and identification submodule 623.
The second interception submodule 621 is configured as intercepting character region from ID Card Image, obtains character figure
Picture.
Second input submodule 622 is configured as inputting character picture in the 3rd convolutional neural networks.
The identification submodule 623 is configured as identifying the character in character picture by the 3rd convolutional neural networks.
In a kind of possible implementation, the device also includes the first training module 66 and the first modular converter 67.
First training module 66 is configured as determining to be categorized as belonging to target image by the first full convolutional network
Before the probability of identity card, the first convolution nerve net for identifying the positive and negative of identity card and the bounding box of identity card is trained
Network.
First modular converter 67 is configured as the first convolutional neural networks being converted to the first full convolutional network.
In a kind of possible implementation, the device also includes the second training module 68 and the second modular converter 69.
Second training module 68 is configured as where the character during target image is determined by the second full convolutional network
Before region, the second convolutional neural networks for identifying character region are trained.
Second modular converter 69 is configured as the second convolutional neural networks being converted to the second full convolutional network.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in relevant this method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
The present embodiment passes through second in the case where determining that target image includes identity card by the first full convolutional network
Full convolutional network determines the character region in target image, passes through the word in the 3rd convolutional neural networks recognition target image
The character of region is accorded with, and the character in target image determines the ID card information in target image, thus, it is possible to fast
ID card information in speed and exactly identification image.
Fig. 8 is a kind of block diagram for being used to identify the device 800 of identity card according to an exemplary embodiment.For example,
Device 800 can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, cure
Treat equipment, body-building equipment, personal digital assistant etc..
Reference picture 8, device 800 can include following one or more assemblies：Processing component 802, memory 804, power supply
Component 806, multimedia groupware 808, audio-frequency assembly 810, the interface 812 of input/output (I/O), sensor cluster 814, and
Communication component 816.
The integrated operation of the usual control device 800 of processing component 802, such as communicated with display, call, data, phase
The operation that machine operates and record operation is associated.Processing component 802 can refer to including one or more processors 820 to perform
Order, to complete all or part of step of above-mentioned method.In addition, processing component 802 can include one or more modules, just
Interaction between processing component 802 and other assemblies.For example, processing component 802 can include multi-media module, it is more to facilitate
Interaction between media component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in device 800.These data are shown
Example includes the instruction of any application program or method for being operated on device 800, contact data, telephone book data, disappears
Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group
Close and realize, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM) are erasable to compile
Journey read-only storage (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 806 provides electric power for the various assemblies of device 800.Power supply module 806 can include power management system
System, one or more power supplys, and other components associated with generating, managing and distributing electric power for device 800.
Multimedia groupware 808 is included in the screen of one output interface of offer between described device 800 and user.One
In a little embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch-screen, to receive the input signal from user.Touch panel includes one or more touch sensings
Device is with the gesture on sensing touch, slip and touch panel.The touch sensor can not only sensing touch or sliding action
Border, but also detect and touched or the related duration and pressure of slide with described.In certain embodiments, more matchmakers
Body component 808 includes a front camera and/or rear camera.When device 800 is in operator scheme, such as screening-mode or
During video mode, front camera and/or rear camera can receive outside multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio-frequency assembly 810 is configured as output and/or input audio signal.For example, audio-frequency assembly 810 includes a Mike
Wind (MIC), when device 800 is in operator scheme, during such as call model, logging mode and speech recognition mode, microphone by with
It is set to reception external audio signal.The audio signal received can be further stored in memory 804 or via communication set
Part 816 is sent.In certain embodiments, audio-frequency assembly 810 also includes a loudspeaker, for exports audio signal.
I/O interfaces 812 provide interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include but be not limited to：Home button, volume button, start button and lock
Determine button.
Sensor cluster 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented
Estimate.For example, sensor cluster 814 can detect opening/closed mode of device 800, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 800, and sensor cluster 814 can be with 800 1 components of detection means 800 or device
Position change, the existence or non-existence that user contacts with device 800, the orientation of device 800 or acceleration/deceleration and device 800
Temperature change.Sensor cluster 814 can include proximity transducer, be configured to detect in no any physical contact
The presence of neighbouring object.Sensor cluster 814 can also include optical sensor, such as CMOS or ccd image sensor, for into
As being used in application.In certain embodiments, the sensor cluster 814 can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device
800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof.In an exemplary implementation
In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 816 also includes near-field communication (NFC) module, to promote junction service.Example
Such as, in NFC module radio frequency identification (RFID) technology can be based on, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application specific integrated circuits (ASIC), numeral
Number processor (DSP), digital signal processing appts (DSPD), PLD (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for performing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided
Such as include the memory 804 of instruction, above-mentioned instruction can be performed to complete the above method by the processor 820 of device 800.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
Those skilled in the art will readily occur to the disclosure its after considering specification and putting into practice invention disclosed herein
Its embodiment.The application is intended to any modification, purposes or the adaptations of the disclosure, these modifications, purposes or
Person's adaptations follow the general principle of the disclosure and including the undocumented common knowledges in the art of the disclosure
Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the disclosure and spirit are by following
Claim is pointed out.
It should be appreciated that the precision architecture that the disclosure is not limited to be described above and is shown in the drawings, and
And various modifications and changes can be being carried out without departing from the scope.The scope of the present disclosure is only limited by appended claim.
Claims (14)
- A kind of 1. method for identifying identity card, it is characterised in that including：It is true by the second full convolutional network in the case where determining that target image includes identity card by the first full convolutional network Character region in the fixed target image；The character of the character region in the target image is identified by the 3rd convolutional neural networks；Character in the target image determines the ID card information in the target image.
- 2. according to the method for claim 1, it is characterised in that methods described also includes：The probability for being categorized as identity card belonging to the target image is determined by the described first full convolutional network；In the case where the probability for being categorized as identity card belonging to the target image meets condition, determine in the target image Including identity card.
- 3. according to the method for claim 1, it is characterised in that determined by the second full convolutional network in the target image Character region, including：Identity card region is intercepted from the target image, obtains ID Card Image；The ID Card Image is inputted in the second full convolutional network；The character region in the ID Card Image is determined by the described second full convolutional network.
- 4. according to the method for claim 3, it is characterised in that identify the target image by the 3rd convolutional neural networks In character region character, including：Character region is intercepted from the ID Card Image, obtains character picture；The character picture is inputted in the 3rd convolutional neural networks；The character in the character picture is identified by the 3rd convolutional neural networks.
- 5. method as claimed in any of claims 2 to 4, it is characterised in that methods described also includes：Determined by the described first full convolutional network belonging to the target image be categorized as the probability of identity card before, training For identifying the first convolutional neural networks of the positive and negative of identity card and the bounding box of identity card；First convolutional neural networks are converted into the described first full convolutional network.
- 6. method as claimed in any of claims 1 to 4, it is characterised in that methods described also includes：Before the character region during the target image is determined by the second full convolutional network, train for identifying character Second convolutional neural networks of region；Second convolutional neural networks are converted into the described second full convolutional network.
- A kind of 7. device for identifying identity card, it is characterised in that including：First determining module, in the case where determining that target image includes identity card by the first full convolutional network, leading to Cross the second full convolutional network and determine character region in the target image；Identification module, for identifying the character of the character region in the target image by the 3rd convolutional neural networks；Second determining module, the ID card information in the target image is determined for the character in the target image.
- 8. device according to claim 7, it is characterised in that described device also includes：3rd determining module, for determining to be categorized as identity card belonging to the target image by the described first full convolutional network Probability；4th determining module, in the case of meeting condition in the probability for being categorized as identity card belonging to the target image, Determine that the target image includes identity card.
- 9. device according to claim 7, it is characterised in that first determining module includes：First interception submodule, for intercepting identity card region from the target image, obtains ID Card Image；First input submodule, for the ID Card Image to be inputted in the second full convolutional network；Determination sub-module, for determining the character region in the ID Card Image by the described second full convolutional network.
- 10. device according to claim 9, it is characterised in that the identification module includes：Second interception submodule, for intercepting character region from the ID Card Image, obtains character picture；Second input submodule, for the character picture to be inputted in the 3rd convolutional neural networks；Submodule is identified, for identifying the character in the character picture by the 3rd convolutional neural networks.
- 11. the device according to any one in claim 8 to 10, it is characterised in that described device also includes：First training module, for determining to be categorized as identity belonging to the target image by the described first full convolutional network Before the probability of card, the first convolutional neural networks for identifying the positive and negative of identity card and the bounding box of identity card are trained；First modular converter, for first convolutional neural networks to be converted into the described first full convolutional network.
- 12. the device according to any one in claim 7 to 10, it is characterised in that described device also includes：Second training module, for the character region in the target image is determined by the second full convolutional network it Before, train the second convolutional neural networks for identifying character region；Second modular converter, for second convolutional neural networks to be converted into the described second full convolutional network.
- A kind of 13. device for identifying identity card, it is characterised in that including：Processor；For storing the memory of processor-executable instruction；Wherein, the processor is configured as the method described in any one in perform claim requirement 1 to 6.
- 14. a kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by computing device, make Processor is able to carry out in claim 1 to 6 method described in any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710852421.0A CN107665354B (en) | 2017-09-19 | 2017-09-19 | Method and device for identifying identity card |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710852421.0A CN107665354B (en) | 2017-09-19 | 2017-09-19 | Method and device for identifying identity card |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107665354A true CN107665354A (en) | 2018-02-06 |
| CN107665354B CN107665354B (en) | 2021-04-23 |
Family
ID=61097209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710852421.0A Active CN107665354B (en) | 2017-09-19 | 2017-09-19 | Method and device for identifying identity card |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107665354B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764226A (en) * | 2018-04-13 | 2018-11-06 | 顺丰科技有限公司 | Image text recognition methods, device, equipment and its storage medium |
| CN108764252A (en) * | 2018-05-07 | 2018-11-06 | 苏州苏相机器人智能装备有限公司 | The positive and negative recognition methods of fancy alloys piece based on machine vision |
| CN108960233A (en) * | 2018-06-13 | 2018-12-07 | 北京小米移动软件有限公司 | Identify the method and device of identity card validity period |
| CN109034050A (en) * | 2018-07-23 | 2018-12-18 | 顺丰科技有限公司 | ID Card Image text recognition method and device based on deep learning |
| CN109145891A (en) * | 2018-06-27 | 2019-01-04 | 上海携程商务有限公司 | Client and its system for identifying the method for identity card, identifying identity card |
| CN109697440A (en) * | 2018-12-10 | 2019-04-30 | 浙江工业大学 | A kind of ID card information extracting method |
| CN109961064A (en) * | 2019-03-20 | 2019-07-02 | 深圳市华付信息技术有限公司 | Identity card text positioning method, device, computer equipment and storage medium |
| CN110135346A (en) * | 2019-05-16 | 2019-08-16 | 深圳市信联征信有限公司 | Identity card automatic identifying method and system based on deep learning |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104978586A (en) * | 2015-06-29 | 2015-10-14 | 百度在线网络技术（北京）有限公司 | Trademark identifying method and apparatus |
| CN105825243A (en) * | 2015-01-07 | 2016-08-03 | 阿里巴巴集团控股有限公司 | Method and device for certificate image detection |
| CN106156712A (en) * | 2015-04-23 | 2016-11-23 | 信帧电子技术（北京）有限公司 | A kind of based on the ID (identity number) card No. recognition methods under natural scene and device |
| CN106295629A (en) * | 2016-07-15 | 2017-01-04 | 北京市商汤科技开发有限公司 | Structured text detection method and system |
| CN106557768A (en) * | 2016-11-25 | 2017-04-05 | 北京小米移动软件有限公司 | The method and device is identified by word in picture |
| CN106682629A (en) * | 2016-12-30 | 2017-05-17 | 佳都新太科技股份有限公司 | Identification number identification algorithm in complicated background |
| CN106778525A (en) * | 2016-11-25 | 2017-05-31 | 北京旷视科技有限公司 | Identity identifying method and device |
| CN106778748A (en) * | 2016-12-30 | 2017-05-31 | 江西憶源多媒体科技有限公司 | Identity card method for quickly identifying and its device based on artificial neural network |
| WO2017101036A1 (en) * | 2015-12-16 | 2017-06-22 | Intel Corporation | Fully convolutional pyramid networks for pedestrian detection |
-
2017
- 2017-09-19 CN CN201710852421.0A patent/CN107665354B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825243A (en) * | 2015-01-07 | 2016-08-03 | 阿里巴巴集团控股有限公司 | Method and device for certificate image detection |
| CN106156712A (en) * | 2015-04-23 | 2016-11-23 | 信帧电子技术（北京）有限公司 | A kind of based on the ID (identity number) card No. recognition methods under natural scene and device |
| CN104978586A (en) * | 2015-06-29 | 2015-10-14 | 百度在线网络技术（北京）有限公司 | Trademark identifying method and apparatus |
| WO2017101036A1 (en) * | 2015-12-16 | 2017-06-22 | Intel Corporation | Fully convolutional pyramid networks for pedestrian detection |
| CN106295629A (en) * | 2016-07-15 | 2017-01-04 | 北京市商汤科技开发有限公司 | Structured text detection method and system |
| CN106557768A (en) * | 2016-11-25 | 2017-04-05 | 北京小米移动软件有限公司 | The method and device is identified by word in picture |
| CN106778525A (en) * | 2016-11-25 | 2017-05-31 | 北京旷视科技有限公司 | Identity identifying method and device |
| CN106682629A (en) * | 2016-12-30 | 2017-05-17 | 佳都新太科技股份有限公司 | Identification number identification algorithm in complicated background |
| CN106778748A (en) * | 2016-12-30 | 2017-05-31 | 江西憶源多媒体科技有限公司 | Identity card method for quickly identifying and its device based on artificial neural network |
Non-Patent Citations (2)
| Title |
|---|
| YILIN SONG: "Online Cost Efficient Customer Recognition System for Retail Analytics", 《2017 IEEE WINTER APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW)》 * |
| 王小丽: "基于OPENCV的身份证图像信息提取研究与实现", 《中国优秀硕士论文全文数据库》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764226A (en) * | 2018-04-13 | 2018-11-06 | 顺丰科技有限公司 | Image text recognition methods, device, equipment and its storage medium |
| CN108764252A (en) * | 2018-05-07 | 2018-11-06 | 苏州苏相机器人智能装备有限公司 | The positive and negative recognition methods of fancy alloys piece based on machine vision |
| CN108764252B (en) * | 2018-05-07 | 2022-05-10 | 苏州苏相机器人智能装备有限公司 | Machine vision-based front and back recognition method for decorative alloy sheet |
| CN108960233A (en) * | 2018-06-13 | 2018-12-07 | 北京小米移动软件有限公司 | Identify the method and device of identity card validity period |
| CN109145891A (en) * | 2018-06-27 | 2019-01-04 | 上海携程商务有限公司 | Client and its system for identifying the method for identity card, identifying identity card |
| CN109145891B (en) * | 2018-06-27 | 2022-08-02 | 上海携程商务有限公司 | Client, method for identifying identity card by client and system for identifying identity card |
| CN109034050A (en) * | 2018-07-23 | 2018-12-18 | 顺丰科技有限公司 | ID Card Image text recognition method and device based on deep learning |
| CN109697440A (en) * | 2018-12-10 | 2019-04-30 | 浙江工业大学 | A kind of ID card information extracting method |
| CN109961064A (en) * | 2019-03-20 | 2019-07-02 | 深圳市华付信息技术有限公司 | Identity card text positioning method, device, computer equipment and storage medium |
| CN110135346A (en) * | 2019-05-16 | 2019-08-16 | 深圳市信联征信有限公司 | Identity card automatic identifying method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107665354B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107665354A (en) | Identify the method and device of identity card | |
| CN103916233B (en) | A kind of information ciphering method and device | |
| CN104980580B (en) | Short message inspection method and device | |
| CN107145800A (en) | Method for protecting privacy and device, terminal and storage medium | |
| CN104391870B (en) | Logistics information acquisition methods and device | |
| CN104731688B (en) | Point out the method and device of reading progress | |
| CN104021350A (en) | Privacy-information hiding method and device | |
| CN107832741A (en) | The method, apparatus and computer-readable recording medium of facial modeling | |
| CN105335754A (en) | Character recognition method and device | |
| CN106790043A (en) | The method and device of message is sent in live application | |
| CN107563994A (en) | The conspicuousness detection method and device of image | |
| CN107784279A (en) | Method for tracking target and device | |
| CN106919629A (en) | The method and device of information sifting is realized in group chat | |
| CN106802741A (en) | The determination method and device and mobile terminal of screen edge touch event | |
| CN107193393A (en) | Input method switching method and device | |
| CN107734178A (en) | Presentation of information processing method, device, equipment and storage medium | |
| CN107330391A (en) | Product information reminding method and device | |
| CN107135147A (en) | Method, device and the computer-readable recording medium of sharing position information | |
| CN105631450A (en) | Character identifying method and device | |
| CN107819740A (en) | Verification method, terminal device, audio amplifier and the server of terminal device | |
| CN106844717A (en) | Webpage search display methods and device | |
| CN107404429A (en) | Circle of friends answering method, device and computer-readable recording medium | |
| US10244367B2 (en) | Short message identification method and device, and storage medium | |
| CN106921958A (en) | The method and apparatus for quitting the subscription of business | |
| CN106845199A (en) | Object authentication method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |